Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3247 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2182. Min Range: -7.2182
Max Act: 7.2182. Min Act: -0.1700
Data Index: 7807755 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.9682. Min Act: -0.1700
Data Index: 8783452 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.7495. Min Act: -0.1700
Data Index: 722981 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.6870. Min Act: -0.1700
Data Index: 8472014 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.6245. Min Act: -0.1700
Data Index: 8733870 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.6245. Min Act: -0.1700
Data Index: 5403911 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.5620. Min Act: -0.1700
Data Index: 3493716 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.5307. Min Act: -0.1700
Data Index: 4368458 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.4995. Min Act: -0.1700
Data Index: 6352917 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.4682. Min Act: -0.1700
Data Index: 446166 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.4370. Min Act: -0.1700
Data Index: 5853532 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.3745. Min Act: -0.1700
Data Index: 903807 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.4057. Min Act: -0.1700
Data Index: 5641435 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.3745. Min Act: -0.1700
Data Index: 8110336 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.3432. Min Act: -0.1700
Data Index: 6229453 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.3120. Min Act: -0.1700
Data Index: 7139088 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.2807. Min Act: -0.1700
Data Index: 4232767 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.2807. Min Act: -0.1700
Data Index: 219123 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.2495. Min Act: -0.1700
Data Index: 1571991 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.2807. Min Act: -0.1700
Data Index: 331294 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19